trade/NewsCrawler
1
0
Fork 0
Code Issues 1 Pull Requests Releases Activity

Compare commits

base: trade:cb4d22014ce132fab2b7976ef9acb0b7852f4b18
Branches Tags
trade:master
...
compare: trade:0158b3092acf6b2b0b4f05e0a291900dbe16c582
Branches Tags
trade:master

1 Commits
cb4d22014c ... 0158b3092a

Author SHA1 Message Date
Myeongjin Jo
0158b3092a etoday title trim 2019-08-07 00:24:11 +09:00
1 changed files with 3 additions and 3 deletions
Expand all files Collapse all files

6
Crawler.cs
View File

@@ -161,8 +161,8 @@ namespace NewsCrawler
foreach (var item in lists) foreach (var item in lists)
{ {
string strTitle = item.SelectSingleNode(".//a").InnerText; string strTitle = item.SelectSingleNode(".//a").InnerText.Trim();
string strTime = item.SelectSingleNode(".//span[contains(@class, 'flash_press')]").InnerText; string strTime = item.SelectSingleNode(".//span[contains(@class, 'flash_press')]").InnerText.Trim();
string strURL = item.SelectSingleNode(".//a").GetAttributeValue("href", ""); string strURL = item.SelectSingleNode(".//a").GetAttributeValue("href", "");
strURL="http://www.etoday.co.kr/news/section/newsview.php?idxno="+Regex.Replace(strURL, @"\D", ""); strURL="http://www.etoday.co.kr/news/section/newsview.php?idxno="+Regex.Replace(strURL, @"\D", "");
@@ -243,7 +243,7 @@ namespace NewsCrawler
foreach(var item in lists) foreach(var item in lists)
{ {
string strTitle = item.SelectSingleNode(".//title").InnerText; string strTitle = item.SelectSingleNode(".//title").InnerText.Trim();
strTitle = strTitle.Substring(iCDATALen, strTitle.Length-iCDATALen-3); strTitle = strTitle.Substring(iCDATALen, strTitle.Length-iCDATALen-3);
string strTime = item.ChildNodes["pubDate"].InnerText; string strTime = item.ChildNodes["pubDate"].InnerText;
DateTime time = Convert.ToDateTime(strTime); DateTime time = Convert.ToDateTime(strTime);